Knowledge-Based Systems最新文献_第9页

Robust deadline-aware network function parallelization framework under demand uncertainty 需求不确定情况下稳健的截止日期感知网络功能并行化框架

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-11-03 DOI: 10.1016/j.knosys.2024.112696

Bo Meng , Amin Rezaeipanah

The orchestration of Service Function Chains (SFCs) in Mobile Edge Computing (MEC) becomes crucial for ensuring efficient service provision, especially under dynamic and uncertain demand. Meanwhile, the parallelization of Virtual Network Functions (VNFs) within an SFC can further optimize resource usage and reduce the risk of deadline violations. However, most existing works formulate the SFC orchestration problem in MEC with deterministic demands and costly runtime resource reprovisioning to handle dynamic demands. This paper introduces a Robust Deadline-aware network function Parallelization framework under Demand Uncertainty (RDPDU) designed to address the challenges posed by unpredictable fluctuations in user demand and resource availability within MEC networks. RDPDU to consider end-to-end latency for SFC assembly by modeling load-dependent processing latency and load-independent propagation latency. Also, RDPDU formulates the problem assuming uncertain demand by Quadratic Integer Programming (QIP) to be resistant to dynamic service demand fluctuations. By discovering dependencies between VNFs, the RDPDU effectively assembles multiple sub-SFCs instead of the original SFC. Finally, our framework uses Deep Reinforcement Learning (DRL) to assemble sub-SFCs with guaranteed latency and deadline. By integrating DRL into the SFC orchestration problem, the framework adapts to changing network conditions and demand patterns, improving the overall system's flexibility and robustness. Experimental evaluations show that the proposed framework can effectively deal with demand fluctuations, latency, deadline, and scalability and improve performance against recent algorithms.

移动边缘计算（MEC）中服务功能链（SFC）的协调对于确保高效的服务提供至关重要，尤其是在动态和不确定的需求下。同时，SFC 中虚拟网络功能（VNF）的并行化可以进一步优化资源使用，降低违反截止日期的风险。然而，大多数现有研究都是以确定性需求和代价高昂的运行时资源重新配置来处理动态需求，从而制定 MEC 中的 SFC 协调问题。本文介绍了需求不确定性下的稳健截止日期感知网络功能并行化框架（RDPDU），旨在应对 MEC 网络中用户需求和资源可用性不可预测波动带来的挑战。RDPDU 通过模拟与负载相关的处理延迟和与负载无关的传播延迟，来考虑 SFC 组装的端到端延迟。此外，RDPDU 还通过二次整数编程（QIP）假设不确定的需求来制定问题，以抵御动态服务需求波动。通过发现 VNF 之间的依赖关系，RDPDU 可以有效地组装多个子 SFC，而不是原始的 SFC。最后，我们的框架使用深度强化学习（DRL）来组装具有保证延迟和截止时间的子 SFC。通过将 DRL 集成到 SFC 协调问题中，该框架可适应不断变化的网络条件和需求模式，从而提高整个系统的灵活性和鲁棒性。实验评估表明，所提出的框架能有效处理需求波动、延迟、截止时间和可扩展性等问题，与最新算法相比性能有所提高。

{"title":"Robust deadline-aware network function parallelization framework under demand uncertainty","authors":"Bo Meng , Amin Rezaeipanah","doi":"10.1016/j.knosys.2024.112696","DOIUrl":"10.1016/j.knosys.2024.112696","url":null,"abstract":"<div><div>The orchestration of Service Function Chains (SFCs) in Mobile Edge Computing (MEC) becomes crucial for ensuring efficient service provision, especially under dynamic and uncertain demand. Meanwhile, the parallelization of Virtual Network Functions (VNFs) within an SFC can further optimize resource usage and reduce the risk of deadline violations. However, most existing works formulate the SFC orchestration problem in MEC with deterministic demands and costly runtime resource reprovisioning to handle dynamic demands. This paper introduces a Robust Deadline-aware network function Parallelization framework under Demand Uncertainty (RDPDU) designed to address the challenges posed by unpredictable fluctuations in user demand and resource availability within MEC networks. RDPDU to consider end-to-end latency for SFC assembly by modeling load-dependent processing latency and load-independent propagation latency. Also, RDPDU formulates the problem assuming uncertain demand by Quadratic Integer Programming (QIP) to be resistant to dynamic service demand fluctuations. By discovering dependencies between VNFs, the RDPDU effectively assembles multiple sub-SFCs instead of the original SFC. Finally, our framework uses Deep Reinforcement Learning (DRL) to assemble sub-SFCs with guaranteed latency and deadline. By integrating DRL into the SFC orchestration problem, the framework adapts to changing network conditions and demand patterns, improving the overall system's flexibility and robustness. Experimental evaluations show that the proposed framework can effectively deal with demand fluctuations, latency, deadline, and scalability and improve performance against recent algorithms.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112696"},"PeriodicalIF":7.2,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MuGIL: A Multi-Graph Interaction Learning Network for Multi-Task Traffic Prediction MuGIL：用于多任务交通预测的多图交互学习网络

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-11-03 DOI: 10.1016/j.knosys.2024.112709

Shuai Liu , Haiyang Yu , Han Jiang , Zhenliang Ma , Zhiyong Cui , Yilong Ren

Recently, multi-task traffic prediction has received increasing attention, as it enables knowledge sharing between heterogeneous variables or regions, thereby improving prediction accuracy while satisfying the prediction requirements of multi-source data in Intelligent Transportation Systems (ITS). However, current studies present two significant challenges. First, they often tend to construct specialized models for a limited set of predictive parameters, which results in a lack of generality. Second, modeling the graph-based multi-task interaction and message passing processes remains difficult due to the heterogeneity of graph structures arising from multi-source traffic data. To address these challenges, this paper proposes a Multi-Graph Interaction Learning Network (MuGIL), characterized by three key innovations: 1) A flexible end-to-end multi-task prediction framework that is generalizable for varied variables or scenarios; 2) A multi-source graph representation module that aligns heterogeneous information through semantic graphs; 3) A novel message passing mechanism for multi-task graph neural networks, which enables effective knowledge among tasks. The model is validated using data from California by comparing it with the state-of-the-art prediction models. The results show that the MuGIL model achieves better prediction performance than these baselines. Ablation experiments further highlight the critical role of the designed multi-source graph representation module and message passing mechanism in the model's success. The MuGIL model we have proposed is now open-sourced at the following link: https://github.com/trafficpre/MuGIL.

近来，多任务交通预测受到越来越多的关注，因为它可以实现异构变量或区域之间的知识共享，从而提高预测精度，同时满足智能交通系统（ITS）对多源数据的预测要求。然而，目前的研究面临两个重大挑战。首先，它们往往倾向于为有限的一组预测参数构建专门的模型，从而导致缺乏通用性。其次，由于多源交通数据产生的图结构的异质性，基于图的多任务交互和消息传递过程的建模仍然很困难。为应对这些挑战，本文提出了多图交互学习网络（MuGIL），该网络有三个主要创新点：1) 灵活的端到端多任务预测框架，可用于各种变量或场景；2) 多源图表示模块，可通过语义图将异构信息整合在一起；3) 多任务图神经网络的新型消息传递机制，可实现任务间的有效认知。通过与最先进的预测模型进行比较，利用加利福尼亚州的数据对该模型进行了验证。结果表明，MuGIL 模型的预测性能优于这些基准模型。消融实验进一步凸显了所设计的多源图表示模块和消息传递机制在模型成功中的关键作用。我们提出的 MuGIL 模型现已开源，链接如下：https://github.com/trafficpre/MuGIL。

{"title":"MuGIL: A Multi-Graph Interaction Learning Network for Multi-Task Traffic Prediction","authors":"Shuai Liu , Haiyang Yu , Han Jiang , Zhenliang Ma , Zhiyong Cui , Yilong Ren","doi":"10.1016/j.knosys.2024.112709","DOIUrl":"10.1016/j.knosys.2024.112709","url":null,"abstract":"<div><div>Recently, multi-task traffic prediction has received increasing attention, as it enables knowledge sharing between heterogeneous variables or regions, thereby improving prediction accuracy while satisfying the prediction requirements of multi-source data in Intelligent Transportation Systems (ITS). However, current studies present two significant challenges. First, they often tend to construct specialized models for a limited set of predictive parameters, which results in a lack of generality. Second, modeling the graph-based multi-task interaction and message passing processes remains difficult due to the heterogeneity of graph structures arising from multi-source traffic data. To address these challenges, this paper proposes a Multi-Graph Interaction Learning Network (MuGIL), characterized by three key innovations: 1) A flexible end-to-end multi-task prediction framework that is generalizable for varied variables or scenarios; 2) A multi-source graph representation module that aligns heterogeneous information through semantic graphs; 3) A novel message passing mechanism for multi-task graph neural networks, which enables effective knowledge among tasks. The model is validated using data from California by comparing it with the state-of-the-art prediction models. The results show that the MuGIL model achieves better prediction performance than these baselines. Ablation experiments further highlight the critical role of the designed multi-source graph representation module and message passing mechanism in the model's success. The MuGIL model we have proposed is now open-sourced at the following link: <span><span>https://github.com/trafficpre/MuGIL</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"306 ","pages":"Article 112709"},"PeriodicalIF":7.2,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-view representation learning with dual-label collaborative guidance 多视角表征学习与双标签协同引导

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-11-02 DOI: 10.1016/j.knosys.2024.112680

Bin Chen , Xiaojin Ren , Shunshun Bai , Ziyuan Chen , Qinghai Zheng , Jihua Zhu

Multi-view Representation Learning (MRL) has recently attracted widespread attention because it can integrate information from diverse data sources to achieve better performance. However, existing MRL methods still have two issues: (1) They typically perform various consistency objectives within the feature space, which might discard complementary information contained in each view. (2) Some methods only focus on handling inter-view relationships while ignoring inter-sample relationships that are also valuable for downstream tasks. To address these issues, we propose a novel Multi-view representation learning method with Dual-label Collaborative Guidance (MDCG). Specifically, we fully excavate and utilize valuable semantic and graph information hidden in multi-view data to collaboratively guide the learning process of MRL. By learning consistent semantic labels from distinct views, our method enhances intrinsic connections across views while preserving view-specific information, which contributes to learning the consistent and complementary unified representation. Moreover, we integrate similarity matrices of multiple views to construct graph labels that indicate inter-sample relationships. With the idea of self-supervised contrastive learning, graph structure information implied in graph labels is effectively captured by the unified representation, thus enhancing its discriminability. Extensive experiments on diverse real-world datasets demonstrate the effectiveness and superiority of MDCG compared with nine state-of-the-art methods. Our code will be available at https://github.com/Bin1Chen/MDCG.

多视图表征学习（Multi-view Representation Learning，MRL）最近引起了广泛关注，因为它可以整合来自不同数据源的信息，从而获得更好的性能。然而，现有的 MRL 方法仍然存在两个问题：（1）它们通常在特征空间内执行各种一致性目标，这可能会丢弃每个视图中包含的互补信息。(2）有些方法只关注处理视图间的关系，而忽略了对下游任务同样有价值的样本间关系。为了解决这些问题，我们提出了一种新颖的多视图表示学习方法--双标签协同引导（MDCG）。具体来说，我们充分挖掘和利用隐藏在多视图数据中的有价值的语义和图信息，以协同指导多视图表示学习过程。通过从不同视图中学习一致的语义标签，我们的方法增强了视图间的内在联系，同时保留了视图的特定信息，这有助于学习一致且互补的统一表征。此外，我们还整合了多个视图的相似性矩阵，以构建表示样本间关系的图标签。在自监督对比学习的理念下，统一表示法能有效捕捉图标签中隐含的图结构信息，从而提高其辨别能力。在各种实际数据集上进行的广泛实验证明，与九种最先进的方法相比，MDCG 是有效和优越的。我们的代码将发布在 https://github.com/Bin1Chen/MDCG 网站上。

{"title":"Multi-view representation learning with dual-label collaborative guidance","authors":"Bin Chen , Xiaojin Ren , Shunshun Bai , Ziyuan Chen , Qinghai Zheng , Jihua Zhu","doi":"10.1016/j.knosys.2024.112680","DOIUrl":"10.1016/j.knosys.2024.112680","url":null,"abstract":"<div><div>Multi-view Representation Learning (MRL) has recently attracted widespread attention because it can integrate information from diverse data sources to achieve better performance. However, existing MRL methods still have two issues: (1) They typically perform various consistency objectives within the feature space, which might discard complementary information contained in each view. (2) Some methods only focus on handling inter-view relationships while ignoring inter-sample relationships that are also valuable for downstream tasks. To address these issues, we propose a novel Multi-view representation learning method with Dual-label Collaborative Guidance (MDCG). Specifically, we fully excavate and utilize valuable semantic and graph information hidden in multi-view data to collaboratively guide the learning process of MRL. By learning consistent semantic labels from distinct views, our method enhances intrinsic connections across views while preserving view-specific information, which contributes to learning the consistent and complementary unified representation. Moreover, we integrate similarity matrices of multiple views to construct graph labels that indicate inter-sample relationships. With the idea of self-supervised contrastive learning, graph structure information implied in graph labels is effectively captured by the unified representation, thus enhancing its discriminability. Extensive experiments on diverse real-world datasets demonstrate the effectiveness and superiority of MDCG compared with nine state-of-the-art methods. Our code will be available at <span><span>https://github.com/Bin1Chen/MDCG</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112680"},"PeriodicalIF":7.2,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PMCN: Parallax-motion collaboration network for stereo video dehazing PMCN：用于立体视频去毛刺的视差-运动协作网络

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-11-02 DOI: 10.1016/j.knosys.2024.112681

Chang Wu , Gang He , Wanlin Zhao , Xinquan Lai , Yunsong Li

Despite progress in learning-based stereo dehazing, few studies have focused on stereo video dehazing (SVD). Existing methods may fall short in the SVD task by not fully leveraging multi-domain information. To address this gap, we propose a parallax-motion collaboration network (PMCN) that integrates parallax and motion information for efficient stereo video fog removal. We delicately design a parallax-motion collaboration block (PMCB) as the critical component of PMCN. Firstly, to capture binocular parallax correspondences more efficiently, we introduce a window-based parallax attention mechanism (W-PAM) in the parallax interaction module (PIM) of PMCB. By horizontally splitting the whole frame into multiple windows and extracting parallax relationships within each window, memory usage and runtime can be reduced. Meanwhile, we further conduct horizontal feature modulation to handle cross-window disparity variations. Secondly, a motion alignment module (MAM) based on deformable convolution explores the temporal correlation in the feature space for an independent view. Finally, we propose a fog-adaptive refinement module (FARM) to refine the features after interaction and alignment. FARM incorporates fog prior information and guides the network in dynamically generating processing kernels for dehazing to adapt to different fog scenarios. Quantitative and qualitative results demonstrate that the proposed PMCN outperforms state-of-the-art methods on both synthetic and real-world datasets. In addition, our PMCN also benefits the accuracy improvement for high-level vision tasks in fog scenes, e.g., object detection and stereo matching.

尽管在基于学习的立体去毛刺方面取得了进展，但很少有研究关注立体视频去毛刺（SVD）。现有的方法可能无法充分利用多域信息，因此在 SVD 任务中存在不足。为了弥补这一不足，我们提出了视差-运动协作网络（PMCN），该网络整合了视差和运动信息，可实现高效的立体视频去雾。我们精心设计了视差-运动协作块（PMCB），作为 PMCN 的关键组成部分。首先，为了更有效地捕捉双眼视差对应，我们在 PMCB 的视差交互模块（PIM）中引入了基于窗口的视差关注机制（W-PAM）。通过将整帧图像水平分割成多个窗口，并提取每个窗口内的视差关系，可以减少内存占用和运行时间。同时，我们还进一步进行了水平特征调制，以处理跨窗口的视差变化。其次，基于可变形卷积的运动配准模块（MAM）探索了独立视图特征空间中的时间相关性。最后，我们提出了雾自适应细化模块（FARM），用于在交互和配准后细化特征。FARM 结合了雾的先验信息，并指导网络动态生成处理内核进行去雾处理，以适应不同的雾场景。定量和定性结果表明，所提出的 PMCN 在合成和实际数据集上的表现都优于最先进的方法。此外，我们的 PMCN 还有利于提高雾场景中高级视觉任务（如物体检测和立体匹配）的准确性。

{"title":"PMCN: Parallax-motion collaboration network for stereo video dehazing","authors":"Chang Wu , Gang He , Wanlin Zhao , Xinquan Lai , Yunsong Li","doi":"10.1016/j.knosys.2024.112681","DOIUrl":"10.1016/j.knosys.2024.112681","url":null,"abstract":"<div><div>Despite progress in learning-based stereo dehazing, few studies have focused on stereo video dehazing (SVD). Existing methods may fall short in the SVD task by not fully leveraging multi-domain information. To address this gap, we propose a parallax-motion collaboration network (PMCN) that integrates parallax and motion information for efficient stereo video fog removal. We delicately design a parallax-motion collaboration block (PMCB) as the critical component of PMCN. Firstly, to capture binocular parallax correspondences more efficiently, we introduce a window-based parallax attention mechanism (W-PAM) in the parallax interaction module (PIM) of PMCB. By horizontally splitting the whole frame into multiple windows and extracting parallax relationships within each window, memory usage and runtime can be reduced. Meanwhile, we further conduct horizontal feature modulation to handle cross-window disparity variations. Secondly, a motion alignment module (MAM) based on deformable convolution explores the temporal correlation in the feature space for an independent view. Finally, we propose a fog-adaptive refinement module (FARM) to refine the features after interaction and alignment. FARM incorporates fog prior information and guides the network in dynamically generating processing kernels for dehazing to adapt to different fog scenarios. Quantitative and qualitative results demonstrate that the proposed PMCN outperforms state-of-the-art methods on both synthetic and real-world datasets. In addition, our PMCN also benefits the accuracy improvement for high-level vision tasks in fog scenes, e.g., object detection and stereo matching.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112681"},"PeriodicalIF":7.2,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142594094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Path relinking strategies for the bi-objective double floor corridor allocation problem 双目标双层走廊分配问题的路径重链接策略

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-30 DOI: 10.1016/j.knosys.2024.112666

Nicolás R. Uribe, Alberto Herrán, J. Manuel Colmenar

The bi-objective Double Floor Corridor Allocation Problem is an operational research problem with the goal of finding the best arrangement of facilities in a layout with two corridors located in two floors, in order to minimize the material handling costs and the corridor length. In this paper, we present a novel approach based on a combination of Path Relinking strategies. To this aim, we propose two greedy algorithms to produce an initial set of non-dominated solutions. In a first stage, we apply an Interior Path Relinking with the aim of improving this set and, in the second stage, apply an Exterior Path Relinking to reach solutions that are unreachable in the first stage. Our extensive experimental analysis shows that our method, after automatic parameter optimization, completely dominates the previous benchmarks, spending shorter computation times. In addition, we provide detailed results for the new instances, including standard metrics for multi-objective problems.

双目标双层走廊分配问题是一个运筹学问题，其目标是在两层楼中有两条走廊的布局中找到最佳的设施安排，以最大限度地降低材料处理成本和走廊长度。在本文中，我们提出了一种基于路径重联策略组合的新方法。为此，我们提出了两种贪婪算法，以生成一组非主导解的初始集。在第一阶段，我们采用内部路径重链接，目的是改进这组解决方案；在第二阶段，我们采用外部路径重链接，以获得第一阶段无法获得的解决方案。我们的大量实验分析表明，在自动优化参数后，我们的方法完全超越了之前的基准测试，花费的计算时间也更短。此外，我们还提供了新实例的详细结果，包括多目标问题的标准指标。

引用次数: 0

MFGCN: Multi-faceted spatial and temporal specific graph convolutional network for traffic-flow forecasting MFGCN：用于交通流量预测的多方面时空特定图卷积网络

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-28 DOI: 10.1016/j.knosys.2024.112671

Jingwen Tian , Liangzhe Han , Mao Chen , Yi Xu , Zhuo Chen , Tongyu Zhu , Leilei Sun , Weifeng Lv

Traffic-flow forecasting is a fundamental issue in Intelligent Transportation Systems. Owing to the natural topological structure of road networks, graph convolutional networks (GCNs) have become one of the most promising components. However, existing methods usually implement graph convolution on a static adjacent matrix to capture the spatial relations between road segments, ignoring the fact that the spatial impact varies across time. Moreover, they always learn the common temporal relations for all segments and fail to capture unique patterns for each distinct node. To address these issues, this study explores time-specific spatial dependencies and node-specific temporal relations to utilize GCN for improved traffic-flow forecasting. First, graph convolution is extended to learn the temporal relations between different time slots. The trained graphs contain unique temporal patterns for each node and share patterns among different nodes. Second, a time-specific spatial graph-learning module is designed to establish dynamic spatial dependencies between traffic nodes, which can vary at different times. Finally, an adaptive pattern-sharing mechanism is proposed to adaptively learn the layer-specific patterns and sharing-across-layer patterns. The proposed model is evaluated on four public real-world traffic datasets, and the results show that it outperforms all state-of-the-art methods on the four real-world datasets.

交通流量预测是智能交通系统的一个基本问题。由于道路网络具有天然的拓扑结构，图卷积网络（GCN）已成为最有前途的组成部分之一。然而，现有方法通常在静态相邻矩阵上实施图卷积，以捕捉路段之间的空间关系，而忽略了空间影响随时间变化的事实。此外，它们总是学习所有路段的共同时间关系，而无法捕捉每个不同节点的独特模式。为了解决这些问题，本研究探讨了特定时间的空间依赖性和特定节点的时间关系，以利用 GCN 改进交通流量预测。首先，对图卷积进行扩展，以学习不同时隙之间的时间关系。经过训练的图包含每个节点的独特时间模式以及不同节点之间的共享模式。其次，设计了一个特定时间的空间图学习模块，以建立交通节点之间的动态空间依赖关系，这些关系在不同时间会发生变化。最后，提出了一种自适应模式共享机制，以自适应地学习特定层模式和跨层模式共享。我们在四个公开的真实世界交通数据集上对所提出的模型进行了评估，结果表明该模型在四个真实世界数据集上的表现优于所有最先进的方法。

{"title":"MFGCN: Multi-faceted spatial and temporal specific graph convolutional network for traffic-flow forecasting","authors":"Jingwen Tian , Liangzhe Han , Mao Chen , Yi Xu , Zhuo Chen , Tongyu Zhu , Leilei Sun , Weifeng Lv","doi":"10.1016/j.knosys.2024.112671","DOIUrl":"10.1016/j.knosys.2024.112671","url":null,"abstract":"<div><div>Traffic-flow forecasting is a fundamental issue in Intelligent Transportation Systems. Owing to the natural topological structure of road networks, graph convolutional networks (GCNs) have become one of the most promising components. However, existing methods usually implement graph convolution on a static adjacent matrix to capture the spatial relations between road segments, ignoring the fact that the spatial impact varies across time. Moreover, they always learn the common temporal relations for all segments and fail to capture unique patterns for each distinct node. To address these issues, this study explores time-specific spatial dependencies and node-specific temporal relations to utilize GCN for improved traffic-flow forecasting. First, graph convolution is extended to learn the temporal relations between different time slots. The trained graphs contain unique temporal patterns for each node and share patterns among different nodes. Second, a time-specific spatial graph-learning module is designed to establish dynamic spatial dependencies between traffic nodes, which can vary at different times. Finally, an adaptive pattern-sharing mechanism is proposed to adaptively learn the layer-specific patterns and sharing-across-layer patterns. The proposed model is evaluated on four public real-world traffic datasets, and the results show that it outperforms all state-of-the-art methods on the four real-world datasets.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"306 ","pages":"Article 112671"},"PeriodicalIF":7.2,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142705193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamical mode recognition of coupled flame oscillators by supervised and unsupervised learning approaches 通过监督和非监督学习方法识别耦合火焰振荡器的动态模式

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-28 DOI: 10.1016/j.knosys.2024.112683

Weiming Xu , Tao Yang , Peng Zhang

Combustion instability in gas turbines and rocket engines, as one of the most challenging problems in combustion research, arises from the complex interactions among flames influenced by chemical reactions, heat and mass transfer, and acoustics. Identifying and understanding combustion instability is essential for ensuring the safe and reliable operation of many combustion systems, where exploring and classifying the dynamical behaviors of complex flame systems is a core task. To facilitate fundamental studies, the present work concerned dynamical mode recognition of coupled flame oscillators made of flickering buoyant diffusion flames, which have gained increasing attention in recent years but are not sufficiently understood. The time series data of flame oscillators were generated through fully validated reacting flow simulations. Due to the limitations of expertise-based models, a data-driven approach was adopted. In this study, a nonlinear dimensional reduction model of variational autoencoder (VAE) was used to project the high dimensional data onto a 2-dimensional latent space. Based on phase trajectories in the latent space, both supervised and unsupervised classifiers were proposed for datasets with and without well-known labeling, respectively. For labeled datasets, we established the Wasserstein-distance-based classifier (WDC) for mode recognition; for unlabeled datasets, we developed a novel unsupervised classifier (GMM-DTW) combining dynamic time warping (DTW) and Gaussian mixture model (GMM). Through comparing with conventional approaches for dimensionality reduction and classification, the proposed supervised and unsupervised VAE-based approaches exhibit a prominent performance across seven assessment metrics for distinguishing dynamical modes, implying their potential extension to dynamical mode recognition in complex combustion problems.

燃气轮机和火箭发动机中的燃烧不稳定性是燃烧研究中最具挑战性的问题之一，它源于受化学反应、热量和质量传递以及声学影响的火焰之间复杂的相互作用。识别和理解燃烧不稳定性对于确保许多燃烧系统的安全可靠运行至关重要，而探索复杂火焰系统的动力学行为并对其进行分类是一项核心任务。为了促进基础研究，本研究涉及由闪烁浮力扩散火焰构成的耦合火焰振荡器的动力学模式识别，近年来，这种火焰振荡器受到越来越多的关注，但人们对它的理解还不够充分。火焰振荡器的时间序列数据是通过充分验证的反应流模拟生成的。由于基于专业知识的模型存在局限性，因此采用了数据驱动的方法。本研究采用变异自动编码器（VAE）的非线性降维模型，将高维数据投射到二维潜空间。根据潜空间中的相位轨迹，分别针对有知名标签和无知名标签的数据集提出了有监督和无监督分类器。对于有标记的数据集，我们建立了基于 Wasserstein-distance 的分类器（WDC）用于模式识别；对于无标记的数据集，我们开发了一种结合动态时间扭曲（DTW）和高斯混合模型（GMM）的新型无监督分类器（GMM-DTW）。通过与传统的降维和分类方法比较，所提出的基于 VAE 的有监督和无监督方法在区分动态模式的七个评估指标方面表现突出，这意味着它们有可能扩展到复杂燃烧问题中的动态模式识别。

{"title":"Dynamical mode recognition of coupled flame oscillators by supervised and unsupervised learning approaches","authors":"Weiming Xu , Tao Yang , Peng Zhang","doi":"10.1016/j.knosys.2024.112683","DOIUrl":"10.1016/j.knosys.2024.112683","url":null,"abstract":"<div><div>Combustion instability in gas turbines and rocket engines, as one of the most challenging problems in combustion research, arises from the complex interactions among flames influenced by chemical reactions, heat and mass transfer, and acoustics. Identifying and understanding combustion instability is essential for ensuring the safe and reliable operation of many combustion systems, where exploring and classifying the dynamical behaviors of complex flame systems is a core task. To facilitate fundamental studies, the present work concerned dynamical mode recognition of coupled flame oscillators made of flickering buoyant diffusion flames, which have gained increasing attention in recent years but are not sufficiently understood. The time series data of flame oscillators were generated through fully validated reacting flow simulations. Due to the limitations of expertise-based models, a data-driven approach was adopted. In this study, a nonlinear dimensional reduction model of variational autoencoder (VAE) was used to project the high dimensional data onto a 2-dimensional latent space. Based on phase trajectories in the latent space, both supervised and unsupervised classifiers were proposed for datasets with and without well-known labeling, respectively. For labeled datasets, we established the Wasserstein-distance-based classifier (WDC) for mode recognition; for unlabeled datasets, we developed a novel unsupervised classifier (GMM-DTW) combining dynamic time warping (DTW) and Gaussian mixture model (GMM). Through comparing with conventional approaches for dimensionality reduction and classification, the proposed supervised and unsupervised VAE-based approaches exhibit a prominent performance across seven assessment metrics for distinguishing dynamical modes, implying their potential extension to dynamical mode recognition in complex combustion problems.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"307 ","pages":"Article 112683"},"PeriodicalIF":7.2,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142698127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-view multi-behavior interest learning network and contrastive learning for multi-behavior recommendation 用于多行为推荐的多视角多行为兴趣学习网络和对比学习

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-28 DOI: 10.1016/j.knosys.2024.112604

Jieyang Su, Yuzhong Chen, Xiuqiang Lin, Jiayuan Zhong, Chen Dong

The recommendation system aims to recommend items to users by capturing their personalized interests. Traditional recommendation systems typically focus on modeling target behaviors between users and items. However, in practical application scenarios, various types of behaviors (e.g., click, favorite, purchase, etc.) occur between users and items. Despite recent efforts in modeling various behavior types, multi-behavior recommendation still faces two significant challenges. The first challenge is how to comprehensively capture the complex relationships between various types of behaviors, including their interest differences and interest commonalities. The second challenge is how to solve the sparsity of target behaviors while ensuring the authenticity of information from various types of behaviors. To address these issues, a multi-behavior recommendation framework based on Multi-View Multi-Behavior Interest Learning Network and Contrastive Learning (MMNCL) is proposed. This framework includes a multi-view multi-behavior interest learning module that consists of two submodules: the behavior difference aware submodule, which captures intra-behavior interests for each behavior type and the correlations between various types of behaviors, and the behavior commonality aware submodule, which captures the information of interest commonalities between various types of behaviors. Additionally, a multi-view contrastive learning module is proposed to conduct node self-discrimination, ensuring the authenticity of information integration among various types of behaviors, and facilitating an effective fusion of interest differences and interest commonalities. Experimental results on three real-world benchmark datasets demonstrate the effectiveness of MMNCL and its advantages over other state-of-the-art recommendation models. Our code is available at https://github.com/sujieyang/MMNCL.

推荐系统旨在通过捕捉用户的个性化兴趣向其推荐物品。传统的推荐系统通常侧重于用户与物品之间目标行为的建模。然而，在实际应用场景中，用户与物品之间会发生各种类型的行为（如点击、收藏、购买等）。尽管最近在对各种行为类型建模方面做出了努力，但多行为推荐仍然面临着两个重大挑战。第一个挑战是如何全面捕捉各类行为之间的复杂关系，包括兴趣差异和兴趣共性。第二个挑战是如何解决目标行为稀少的问题，同时确保各类行为信息的真实性。为了解决这些问题，我们提出了一个基于多视角多行为兴趣学习网络和对比学习（MMNCL）的多行为推荐框架。该框架包括一个多视角多行为兴趣学习模块，该模块由两个子模块组成：行为差异感知子模块和行为共性感知子模块。前者用于捕捉每种行为类型的行为内兴趣以及各种行为类型之间的相关性，后者用于捕捉各种行为类型之间的兴趣共性信息。此外，还提出了多视角对比学习模块，用于进行节点自辨，确保各类行为之间信息整合的真实性，促进兴趣差异和兴趣共性的有效融合。在三个真实世界基准数据集上的实验结果证明了 MMNCL 的有效性，以及与其他最先进推荐模型相比的优势。我们的代码见 https://github.com/sujieyang/MMNCL。

{"title":"Multi-view multi-behavior interest learning network and contrastive learning for multi-behavior recommendation","authors":"Jieyang Su, Yuzhong Chen, Xiuqiang Lin, Jiayuan Zhong, Chen Dong","doi":"10.1016/j.knosys.2024.112604","DOIUrl":"10.1016/j.knosys.2024.112604","url":null,"abstract":"<div><div>The recommendation system aims to recommend items to users by capturing their personalized interests. Traditional recommendation systems typically focus on modeling target behaviors between users and items. However, in practical application scenarios, various types of behaviors (e.g., click, favorite, purchase, etc.) occur between users and items. Despite recent efforts in modeling various behavior types, multi-behavior recommendation still faces two significant challenges. The first challenge is how to comprehensively capture the complex relationships between various types of behaviors, including their interest differences and interest commonalities. The second challenge is how to solve the sparsity of target behaviors while ensuring the authenticity of information from various types of behaviors. To address these issues, a multi-behavior recommendation framework based on Multi-View Multi-Behavior Interest Learning Network and Contrastive Learning (MMNCL) is proposed. This framework includes a multi-view multi-behavior interest learning module that consists of two submodules: the behavior difference aware submodule, which captures intra-behavior interests for each behavior type and the correlations between various types of behaviors, and the behavior commonality aware submodule, which captures the information of interest commonalities between various types of behaviors. Additionally, a multi-view contrastive learning module is proposed to conduct node self-discrimination, ensuring the authenticity of information integration among various types of behaviors, and facilitating an effective fusion of interest differences and interest commonalities. Experimental results on three real-world benchmark datasets demonstrate the effectiveness of MMNCL and its advantages over other state-of-the-art recommendation models. Our code is available at <span><span>https://github.com/sujieyang/MMNCL</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112604"},"PeriodicalIF":7.2,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FS-PTL: A unified few-shot partial transfer learning framework for partial cross-domain fault diagnosis under limited data scenarios FS-PTL：用于有限数据情况下部分跨域故障诊断的统一少量部分转移学习框架

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-28 DOI: 10.1016/j.knosys.2024.112658

Liu Cheng , Haochen Qi , Rongcai Ma , Xiangwei Kong , Yongchao Zhang , Yunpeng Zhu

Traditional supervised learning-based fault-diagnosis models often encounter performance degradation when data distribution shifts occur. Although unsupervised transfer learning can address such issues, most existing methods face challenges arising from partial cross-domain diagnostic scenarios with limited training data. Therefore, this study introduces a unified few-shot partial-transfer learning framework, specifically designed to address the limitations of data scarcity and partial cross-domain diagnosis applicability. Our framework innovatively takes ridge regression-based feature reconstruction as a nexus to integrate episodic learning with an episodic pretext task and weighted feature alignment, thereby enhancing model adaptability across varying working conditions with minimal data. Specifically, the episodic pretext task enables the learned features with generalization abilities in a self-supervised manner to mitigate meta-overfitting. Weighted feature alignment is performed at the reconstructed feature level, allowing partial transfer with a significantly increased number of features, while further reducing overfitting. Experiments conducted on two distinct datasets revealed that the proposed method outperforms existing state-of-the-art approaches, demonstrating superior transfer performance and robustness under the conditions of limited fault samples.

当数据分布发生变化时，传统的基于监督学习的故障诊断模型往往会遇到性能下降的问题。虽然无监督转移学习可以解决这些问题，但大多数现有方法都面临着部分跨域诊断场景和有限训练数据带来的挑战。因此，本研究引入了一个统一的少量部分转移学习框架，专门用于解决数据稀缺和部分跨域诊断适用性的限制。我们的框架以基于脊回归的特征重构为纽带，创新性地将外显学习与外显借口任务和加权特征对齐整合在一起，从而在数据极少的情况下增强了模型在不同工作条件下的适应性。具体来说，外显前置任务以自我监督的方式使学习到的特征具有泛化能力，从而减轻元过拟合。加权特征对齐是在重构特征水平上进行的，允许在特征数量显著增加的情况下进行部分转移，同时进一步减少过拟合。在两个不同的数据集上进行的实验表明，所提出的方法优于现有的最先进方法，在故障样本有限的条件下表现出卓越的转移性能和鲁棒性。

{"title":"FS-PTL: A unified few-shot partial transfer learning framework for partial cross-domain fault diagnosis under limited data scenarios","authors":"Liu Cheng , Haochen Qi , Rongcai Ma , Xiangwei Kong , Yongchao Zhang , Yunpeng Zhu","doi":"10.1016/j.knosys.2024.112658","DOIUrl":"10.1016/j.knosys.2024.112658","url":null,"abstract":"<div><div>Traditional supervised learning-based fault-diagnosis models often encounter performance degradation when data distribution shifts occur. Although unsupervised transfer learning can address such issues, most existing methods face challenges arising from partial cross-domain diagnostic scenarios with limited training data. Therefore, this study introduces a unified few-shot partial-transfer learning framework, specifically designed to address the limitations of data scarcity and partial cross-domain diagnosis applicability. Our framework innovatively takes ridge regression-based feature reconstruction as a nexus to integrate episodic learning with an episodic pretext task and weighted feature alignment, thereby enhancing model adaptability across varying working conditions with minimal data. Specifically, the episodic pretext task enables the learned features with generalization abilities in a self-supervised manner to mitigate meta-overfitting. Weighted feature alignment is performed at the reconstructed feature level, allowing partial transfer with a significantly increased number of features, while further reducing overfitting. Experiments conducted on two distinct datasets revealed that the proposed method outperforms existing state-of-the-art approaches, demonstrating superior transfer performance and robustness under the conditions of limited fault samples.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112658"},"PeriodicalIF":7.2,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intelligent fault diagnosis for tribo-mechanical systems by machine learning: Multi-feature extraction and ensemble voting methods 通过机器学习对三机械系统进行智能故障诊断：多特征提取和集合投票法

IF 7.2 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Knowledge-Based Systems

Pub Date : 2024-10-28 DOI: 10.1016/j.knosys.2024.112694

V. Shandhoosh , Naveen Venkatesh S , Ganjikunta Chakrapani , V. Sugumaran , Sangharatna M. Ramteke , Max Marian

Timely fault detection is crucial for preventing issues like worn clutch plates and excessive friction material degradation, enhancing fuel efficiency, and prolonging clutch lifespan. This study focuses on early fault diagnosis in dry friction clutch systems using machine learning (ML) techniques. Vibration data is analyzed under different load and fault conditions, extracting statistical, histogram, and auto-regressive moving average (ARMA) features. Feature selection employs the J48 decision tree algorithm, evaluated with eight ML classifiers: support vector machines (SVM), k-nearest neighbor (kNN), linear model tree (LMT), random forest (RF), multilayer perceptron (MLP), logistic regression (LR), J48, and Naive Bayes. The evaluation revealed that individual classifiers achieved the highest testing accuracies with statistical feature selection as 83% for both MLP and LR at no load, 90% for MLP at 5 kg, and 93% for KNN at 10 kg. For histogram feature selection, KNN and MLP both reached 85% at no load, MLP achieved 91% at 5 kg, and RF attained 97% at 10 kg. With ARMA feature selection, KNN reached 93% at no load, LR achieved 94% at 5 kg, and RF reached 86% at 10 kg. The voting strategy notably improved these results, with the RF-KNN-J48 ensemble reaching 98% for histogram features at 10 kg, the KNN-LMT-RF ensemble achieving 94% for ARMA features at no load, and the SVM-MLP-LMT ensemble attaining 95% for ARMA features at 5 kg. Hence, a combination of three classifiers using the majority voting rule consistently outperforms standalone classifiers, striking a balance between diversity and complexity, facilitating robust decision-making. In practical applications, selecting the optimal combination of feature selection method and classifier is vital for accurate fault classification. This study provides valuable guidance for engineers and practitioners implementing robust load classification systems in industrial settings.

及时发现故障对于防止离合器片磨损和摩擦材料过度降解等问题、提高燃油效率和延长离合器使用寿命至关重要。本研究的重点是利用机器学习（ML）技术对干摩擦离合器系统进行早期故障诊断。在不同负载和故障条件下对振动数据进行分析，提取统计、直方图和自动回归移动平均（ARMA）特征。特征选择采用了 J48 决策树算法，并用以下八种 ML 分类器进行了评估：支持向量机 (SVM)、k-近邻 (kNN)、线性模型树 (LMT)、随机森林 (RF)、多层感知器 (MLP)、逻辑回归 (LR)、J48 和 Naive Bayes。评估结果显示，在统计特征选择方面，单个分类器在空载时的测试准确率最高，MLP 和 LR 均为 83%，MLP 在 5 千克时为 90%，KNN 在 10 千克时为 93%。在直方图特征选择方面，KNN 和 MLP 在空载时均达到 85%，MLP 在 5 千克时达到 91%，RF 在 10 千克时达到 97%。对于 ARMA 特征选择，KNN 在空载时达到 93%，LR 在 5 千克时达到 94%，RF 在 10 千克时达到 86%。投票策略明显改善了这些结果，RF-KNN-J48 组合在 10 千克时的直方图特征得分率达到 98%，KNN-LMT-RF 组合在空载时的 ARMA 特征得分率达到 94%，SVM-MLP-LMT 组合在 5 千克时的 ARMA 特征得分率达到 95%。因此，使用多数投票规则的三种分类器组合始终优于独立的分类器，在多样性和复杂性之间取得了平衡，有助于做出稳健的决策。在实际应用中，选择特征选择方法和分类器的最佳组合对于准确的故障分类至关重要。这项研究为工程师和从业人员在工业环境中实施稳健负载分类系统提供了宝贵的指导。

{"title":"Intelligent fault diagnosis for tribo-mechanical systems by machine learning: Multi-feature extraction and ensemble voting methods","authors":"V. Shandhoosh , Naveen Venkatesh S , Ganjikunta Chakrapani , V. Sugumaran , Sangharatna M. Ramteke , Max Marian","doi":"10.1016/j.knosys.2024.112694","DOIUrl":"10.1016/j.knosys.2024.112694","url":null,"abstract":"<div><div>Timely fault detection is crucial for preventing issues like worn clutch plates and excessive friction material degradation, enhancing fuel efficiency, and prolonging clutch lifespan. This study focuses on early fault diagnosis in dry friction clutch systems using machine learning (ML) techniques. Vibration data is analyzed under different load and fault conditions, extracting statistical, histogram, and auto-regressive moving average (ARMA) features. Feature selection employs the J48 decision tree algorithm, evaluated with eight ML classifiers: support vector machines (SVM), k-nearest neighbor (kNN), linear model tree (LMT), random forest (RF), multilayer perceptron (MLP), logistic regression (LR), J48, and Naive Bayes. The evaluation revealed that individual classifiers achieved the highest testing accuracies with statistical feature selection as 83% for both MLP and LR at no load, 90% for MLP at 5 kg, and 93% for KNN at 10 kg. For histogram feature selection, KNN and MLP both reached 85% at no load, MLP achieved 91% at 5 kg, and RF attained 97% at 10 kg. With ARMA feature selection, KNN reached 93% at no load, LR achieved 94% at 5 kg, and RF reached 86% at 10 kg. The voting strategy notably improved these results, with the RF-KNN-J48 ensemble reaching 98% for histogram features at 10 kg, the KNN-LMT-RF ensemble achieving 94% for ARMA features at no load, and the SVM-MLP-LMT ensemble attaining 95% for ARMA features at 5 kg. Hence, a combination of three classifiers using the majority voting rule consistently outperforms standalone classifiers, striking a balance between diversity and complexity, facilitating robust decision-making. In practical applications, selecting the optimal combination of feature selection method and classifier is vital for accurate fault classification. This study provides valuable guidance for engineers and practitioners implementing robust load classification systems in industrial settings.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"305 ","pages":"Article 112694"},"PeriodicalIF":7.2,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0